RAPID QUANTITATIVE-ANALYSIS OF BINARY-MIXTURES OF ESCHERICHIA-COLI STRAINS USING PYROLYSIS MASS-SPECTROMETRY WITH MULTIVARIATE CALIBRATION AND ARTIFICIAL NEURAL NETWORKS

Pyrolysis mass spectrometry (PyMS) and multivariate calibration were u sed to show the high degree of relatedness between Escherichia coli HB 101 and E. coli UB5201. Next, binary mixtures of these two phenotypica lly closely related E. cold strains were prepared and subjected to PyM S. Fully interconnected feedforward artificial neural networks (ANN's) were used to analyse the pyrolysis mass spectra to obtain quantitativ e information representative of the level of E. coli UB5201 in E. coli HB101. The ANNs exploited were trained using the standard back propag ation algorithm, and the nodes used sigmoidal squashing functions. Acc urate quantitative information vc as obtained for mixtures with > 3% E . coli UB5201 in E. coli HB101. To remove noise from the pyrolysis mas s spectra and so lower the limit of detection, the spectra were reduce d using principal components analysis (PCA) and the first 13 principal components used to train ANNs. These PCA-ANNs allowed accurate estima tes at levels as low as 1% E. coli UB5201 in E. coli HB101 to be predi cted. In terms of bacterial numbers, it was shown that the limit of de tection for PyMS in conjunction with ANNs was 3 x 10(4) E. coli UB5201 cells in 1.6 x 10(7) E. coli HB101 cells. It may be concluded that Pr MS with ANNs provides a powerful and rapid method for the quantificati on of mixtures of closely related bacterial strains..